A machine learning apparatus that learns a condition associated with a predicted life of a motor includes: a state observation unit that observes a state variable composed from at least one of output data of a sensor that detects an operation state of the motor and data relating to presence or absence of a failure in the motor; an actual life data acquisition unit that acquires data relating to an actual life of the motor; and a learning unit that learns the condition associated with the predicted life of the motor in accordance with a training data set created based on a combination of the state variable and the actual life.

The present invention enables to easily and accurately measure a joint of a robot apparatus, in particular, a lost motion of a driving system of the joint, and, to easily and accurately perform a diagnosis of a lifetime or a life expectancy of a joint mechanism of the robot apparatus based on a measured result.